Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 12

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  measurement invariance
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1

School autonomy – a cross-national perspective. Can we compare the opinion of school principals?

100%
Węziak-Białowolska, D., Isac M. M.
Edukacja
|
2014
|
issue 4(129)
5–20
XX
Perception of school autonomy was measured by the International Civic and Citizenship Education Study (ICCS) 2009, allowing potential cross-national comparison. The possibility of a common, general scale for all countries participating in the study was investigated. Using multi-group confirmatory and exploratory factor analysis, measurement invariance was tested for countries, such that meaningful comparisons for the concept could be made. The results show that the concept is not necessarily comparable between all countries involved in the ICCS but that secondary data analysis is generally feasible depending on the research questions posed and the methodology applied. The scientific and practical implications of this reach are discussed.
2
Publication available in full text mode
Content available

Survey-based household inflation expectations. Are they valid? A multi-group confirmatory factor analysis approach

88%
Białowolski P.
Prace i Materiały Instytutu Rozwoju Gospodarczego SGH
|
2015
|
vol. 96: Analyzing and forecasting economic fluctuations
49-67
EN
We present evidence that micro-level household inflation expectations are influenced by consumer confidence. To account for this impact, using multi-group confirmatory factor analysis, we measure the intertemporal consistency of a model comprising both consumer confidence and inflation expectations. We determine that the model exhibits the property of partial measurement invariance. Thus, we are able to account reliably for the influence of consumer confidence on inflation expectations and, simultaneously, to obtain corrected inflation expectations at the household level. It appears that, after correcting for the level of confidence, average inflation expectations at each point in time become significantly more similar to the average inflation expectations of professional forecasters and more correlated with average consumer confidence. Our analysis is based on household survey data from Poland’s State of the Households’ Survey (from 2000Q1 to 2012Q1), which is conducted in line with the European Commission’s methodology.
3
Content available remote

The psychometric properties of the Meaning in Life Questionnaire in Slovakia

88%
Halama P., Kohútová V., Havan P., Kohút M.
Československá psychologie (Czechoslovak Psychology)
|
2024
|
vol. 68
|
issue 1
49-66
EN
Objectives. The study focuses on the psychometric examination of the Meaning in Life Questionnaire (MLQ) in a Slovak translation. Sample and settings. The sample consisted of 1368 Slovak participants (mean age 41.58 years). To assess the questionnaire's stability over time and predictive power, a subset of participants (421 adults) was invited to retest after approximately six months. Statistical analyses. Confirmatory factor analysis (CFA) was performed to assess the internal structure of the MLQ and its measurement invariance across gender and age groups. Item response theory (IRT) using a single-factor generalized partial credit model was applied for item analysis. Hierarchical linear regression analysis was performed to examine the predictive power of the MLQ. Results. The MLQ showed good internal consistency for both subscales, but the CFA showed perfect fit only for the Presence of Meaning subscale; fit for the Search for Meaning subscale was borderline acceptable. Both subscales were found to be invariant across gender and age groups. Correlation analysis revealed positive associations between Presence of meaning and subjective well-being, whereas Search for meaning was only weakly correlated or not correlated at all. Longitudinal analysis revealed that the Presence of meaning (but not the Search for meaning) significantly predicted life satisfaction after controlling for personality and emotion-based measures of well-being. Limitations. The limitation of the study is specific sample recruited through a research panel agency based on self-selection of participant.
4
Publication available in full text mode
Content available

Consumer confidence, durable goods purchase and unemployment forecast

88%
Białowolski P.
Econometrics. Ekonometria. Advances in Applied Data Analytics
|
2014
|
issue 3(45)
42-55
EN
Multi-Group Confirmatory Factor Analysis (MGCFA) demonstrated the deficiency of the four original European Commission (EC) items for consumer confidence. Fit of the MGCFA model was unacceptable and without scalar invariance, index comparison between study periods was not permissible. This provided clear motivation for a plausible alternative index specification to comply with requirements for single-dimensionality and meaning invariance throughout the study period. The MGCFA model using a new set of items demonstrated partial metric and partial scalar invariance. Using the structural equation framework, consumer confidence was revealed as strongly interrelated with unemployment forecast and durable goods purchase.
5
Content available remote

Česká adaptace dotazníku Multidimensional Health Locus of Control Scale: konfirmační faktorová analýza a invariance měření

75%
Kostolanská E., Řiháček T., Stehlíková J., Cígler H.
Československá psychologie (Czechoslovak Psychology)
|
2020
|
vol. 64
|
issue 5
521-534
EN
Aim. Measuring patients’ health-related beliefs is of high importance in health care. The aim of the study was to test the factor structure of the Czech version of the Multidimensional Health Locus of Control Scale (MHLCS) Form B and its measurement invariance. Method. N = 549 adults answered the MHLCS in an online survey. A confirmatory factor analysis was conducted to test three competing models based on previous studies and to assess measurement invariance of the MHLCS across gender, age, and time (six months). Results. None of the hypothesized models fit the data; therefore, a modified three-factor model was proposed that demonstrated an acceptable fit and was strictly invariant with respect to gender, age, and time. A small age effect was found on the Powerful Others and Chance factors. Conclusion. The Czech MHLCS can be considered a valid and reliable measure, except for the Chance factor, which had low reliability.
CS
Cíl. Měření přesvědčení, která se vztahují ke zdraví, má u pacientů ve zdravotnictví velký význam. Cílem studie bylo ověřit faktorovou strukturu české verze dotazníku Multidimensional Health Locus of Control Scale (MHLCS, verze B) a její invarianci. Metoda. N = 549 dospělých respondentů vyplnilo MHLCS v online průzkumu. Pomocí konfirmační faktorové analýzy byly ověřovány tři modely založené na předchozích studiích a dále byla ověřována invariance měření v závislosti na pohlaví, věku a času (šest měsíců). Výsledky. Žádný z navržených modelů nevykazoval dostatečnou shodu s daty. Proto byl navržen modifikovaný třífaktorový model, který vykázal přijatelnou shodu s daty a byl striktně invariantní ve vztahu k pohlaví, věku i času. U faktorů Vlivní druzí a Náhoda byl nalezen slabý efekt věku. Závěr. Českou verzi MHLCS lze považovat za validní a reliabilní nástroj, s výjimkou faktoru Náhoda, který vykazoval nízkou reliabilitu.
6
Content available remote

Cooper-Norcross Inventory of Preferences (C-NIP): psychometric characteristics of the Czech version

75%
Řiháček T., Mikutová M.
Československá psychologie (Czechoslovak Psychology)
|
2022
|
vol. 66
|
issue 2
145-156
EN
Objective. The Cooper-Norcross Inventory of Preferences (C-NIP) is a new and promising tool for measuring clients’ preferences regard-ing psychotherapy. However, the psychometric evaluation of this measure is scarce in general and completely missing for the Czech adapta-tion of the measure. This study aimed to test the Czech version of the C-NIP factor structure, test its measurement invariance, and establish cut points. Methods.N = 772 adults answered the C-NIP in an online survey. Confirmatory and explora-tory factor analyses were used to test the fac-tor structure and assess the C-NIP measurement invariance between men and women and across several levels of psychotherapy experience.Results. The original four-factor model was not supported. Instead, a five-factor model was sug-gested that fit the data adequately and was strict-ly invariant with respect to gender and levels of experience with psychotherapy. Conclusions. The Czech C-NIP can be con-sidered a valid and reliable measure of clients’ preferences regarding psychotherapy. The repli-cation of the new factor model is needed.
CS
Cíl. Cooper-Norcross Inventory of Preferences (C-NIP) představuje nejnovější a slibný nástroj určený k měření preferencí klientů ve vztahu k psychoterapii. Psychometrické zhodnocení to-hoto nástroje je však zatím sporé a u české verze zcela chybí. Cílem této studie bylo ověřit fakto-rovu strukturu české verze C-NIP, ověřit invari-anci měření a stanovit hraniční skóry. Metody.N = 772 dospělých respondentů vypl-nilo C-NIP v online průzkumu. K ověření fak-torové struktury a invariance měření mezi po-hlavími a napříč různými úrovněmi zkušenosti s psychoterapií byla použita konfirmační fakto-rový analýza. Výsledky. Původní faktorová struktura nebyla podpořena. Namísto toho byl navržen pětifak-torový model, který vykazoval adekvátní shodu s daty a byl striktně invariantní ve vztahu k po-hlaví i úrovni zkušenosti s psychoterapií. Závěr. Českou verzi C-NIP lze považovat za validní a reliabilní nástroj na měření preferencí klientů ve vztahu k psychoterapii. Je zapotřebí replikovat navrženou faktorovou strukturu.
7
Content available remote

Hong psychological reactance scale: factorial structure and measurement invariance of the Czech version

75%
Stehlíková J., Řiháček T., Kostolanská E., Cígler H.
Československá psychologie (Czechoslovak Psychology)
|
2020
|
vol. 64
|
issue 6
656-667
EN
Objective. Psychological reactance is a construct of high practical utility in health care and other areas. However, no clear consensus has been achieved regarding its structure. This study aimed to test the factor structure of the Czech version of the Hong Psychological Reactance Scale (HPRS) and to test its measurement invariance. Methods. N = 544 adults answered the HPRS in an online survey. Confirmatory factor analysis was used to test five competing models based on previous studies and to assess the measurement invariance of the HPRS across gender and age. Results. None of the hypothesized models fit the data. Authors proposed a new bifactor model that fit the data adequately and was strictly invariant with respect to gender, but not across two age groups. Conclusions. The Czech HPRS can be considered a reliable measure of the general reactance across both genders but caution must be exercised when comparing reactance across different age groups. Replication of the new model is needed.
CS
Cíl. Psychologická reaktance je velmi užitečným konstruktem ve zdravotnictví a dalších oblastech. Zatím však nepanuje jednoznačná shoda ohledně jeho struktury. Cílem této studie bylo ověřit faktorovou strukturu české verze Hongovy škály psychologické reaktance (HPRS) a její invarianci. Metody. N = 544 dospělých respondentů vyplnilo HPRS v online průzkumu. Pomocí konfirmační faktorové analýzy bylo ověřováno pět modelů založených na předchozích studiích, a dále invariance měření ve vztahu k pohlaví a věku. Výsledky. Žádný z navrhovaných modelů nevykazoval dostatečnou shodu s daty. Proto byl navržen nový bifaktorový model, který vykazoval dostatečnou shodu s daty a striktní invarianci vzhledem k pohlaví, ne však k věku. Závěry. Českou verzi HPRS lze považovat za spolehlivé měřítko obecné reaktance u obou pohlaví, ale při porovnávání míry reaktance mezi různými věkovými skupinami je zapotřebí opatrnosti. Je nutná replikace nového modelu.
8
Content available remote

Evaluating Measurement Invariance for Social and Political Trust in Western Europe over Four Measurement Time Points (2002-2008)

75%
Coromina L., Davidov E.
ASK. Research and Methods
|
2013
|
vol. 22
37-54
EN
It is a well-documented fact that social trust, i.e., the extent to which people trust others, and political trust, i.e., trust in political institutions, are key factors in social capital theory. However, to compare these concepts in cross-national or longitudinal frameworks, it is important to first establish whether the measurements of these concepts are compatible across countries or over time. This paper tests the measurement and cross-national and longitudinal invariance properties of social and political trust. We use multiple-group confirmatory factor analyses (MGCFA) to evaluate the different levels of invariance (configural, metric and scalar) using data from the European Social Survey (ESS) measured at four different time points (2002, 2004, 2006 and 2008) in seven Western European countries. In a second step, the country mean rankings of social and political trust are computed based on the latent scores and compared with those based on traditional sum score measurements. This comparison illustrates the potential inaccuracy of sum scores for country mean comparisons when measurement invariance is not supported by the data.
9
Content available remote

Testování psychometrických vlastností a ekvivalence české verze škály spokojenosti se životem (SWLS) pomocí metod konfirmační faktorové analýzy, teorie odpovědi na položku a bayesovského modelování

75%
Hanzlová R., Raudenská P.
Sociologický časopis. Czech Sociological Review
|
2024
|
vol. 60
|
issue 1
37-66
EN
The Satisfaction with Life Scale (SWLS) is one of the most commonly used instruments for measuring life satisfaction. The aim of this study is to test the psychometric properties of the Czech version of the SWLS using Confirmatory Factor Analysis (CFA) and Item Response Theory (IRT) and to test its invariance between social groups in terms of gender, age, and education using Bayesian modelling on a representative sample of the Czech online population, as the scale has not yet been tested on representative data in the Czech Republic. The research sample consists of 960 respondents aged 18 to 69 years. The results confirmed that the psychometric properties of the Czech version of the SWLS are very good, but, at the same time, it is evident that the fifth item shows worse results than the other four items. In terms of dimensionality, CFA and IRT confirmed its modified single-factor structure with correlated residuals between the fourth and fifth items as the most appropriate. Testing for approximate measurement invariance using Bayesian modelling showed that the SWLS measures comparably between groups based on gender, age, and education. In conclusion, the Czech version of the SWLS is a suitable, verified, and reliable instrument for measuring the life satisfaction of Czech citizens.
10
Publication available in full text mode
Content available

Psychometric properties of the Polish version of the Generalized Anxiety Disorder Scale (GAD-7) in a non-clinical sample of employees during pandemic crisis

75%
Basińska B. A., Kwissa-Gajewska Z.
International Journal of Occupational Medicine and Environmental Health
|
2023
|
vol. 36
|
issue 4
493-504
EN
Objectives The COVID-19 outbreak is an example of a crisis that triggered an increase in generalized anxiety disorder. The study aims to validate the Polish version of the Generalized Anxiety Disorder 7-item scale (GAD-7) by Spitzer et al. among a non-clinical sample of employees and examine the invariance depending on the gender and age of working adults. Material and Methods For assessing factor structure of the Polish version of the GAD-7, the data were collected from a sample of 821 adults employed in 4 economic sectors (health care, education, IT, public administration) during the initial phase of the COVID-19 pandemic in Poland (April 10–May 24, 2020). Due to differences in the severity of GAD symptoms across gender and age groups, the measurement invariance in these groups was tested. Results The results of a series of confirmatory factor analyses confirmed the unidimensionality of the GAD-7. The values of the composite reliability index and Cronbach’s α showed that it is a reliable tool. The GAD levels demonstrated strong relationships with professional burnout, psychological distress, and psychological complaints. These relationships were stronger than the relationships between these factors and job satisfaction. Construct, metric and scalar invariance across gender and age groups were documented. Women experienced more severe symptoms of generalized anxiety disorder than men. Generalized anxiety disorder affected 28% of respondents. Conclusions This study contributes evidence of the validation of the GAD among employees and also confirms the invariance depending on gender and age. The Polish version of the GAD-7 has good psychometric properties in a group of professionals and can be recommended for research and to be used in an occupational medicine practice, especially during crisis periods associated with the risk of developing a generalized anxiety disorder.
11
Content available remote

Czech version of the outcome rating scale: selected psychometric properties

63%
Seryjová Juhová D., Řiháček T., Cígler H., Dubovská E., Saic M., Černý M., Dufek J., Miller S. D.
Československá psychologie (Czechoslovak Psychology)
|
2021
|
vol. 65
|
issue 4
353-368
EN
Objectives. The Outcome Rating Scale (ORS) is an ultra-brief self-report scale designed to measure change during psychotherapy. The goal of this study was to test (a) the factor structure of the ORS, (b) the measurement invariance between a clinical and a non-clinical sample, between pre-therapy and post-therapy assessment (within the clinical sample), and between online and paper-and-pencil forms of administration (within the non-clinical sample), (c) concurrent validity with other outcome measures, and (d) sensitivity to therapeutic change. Sample and settings. N = 256 patients, N = 210 non-clinical respondents, and N = 89 students participated in the study. Patients responded to the ORS before and after psychotherapy. Statistical analysis. The factor structure and measurement invariance were tested using confirmatory factor analysis. Concurrent validity and test-retest reliability were assessed using correlational analysis. Sensitivity to change was assessed using the Reliable Change Index and pre-post effect size. Results. The unidimensional structure was supported. The best-fitting model was a partially tau-equivalent model with the first and the fourth items’ loadings fixed to the same value. While only metric invariance was demonstrated between the clinical and non-clinical samples, the ORS demonstrated scalar invariance between pre- and post-therapy assessment and strict invariance between the paper-and-pencil and online forms of administration. Internal consistency, as well as concurrent validity, were satisfactory. The sensitivity to the therapeutic change was adequate. Furthermore, internal consistency and sensitivity to change were increased if the score was computed as a weighted sum of items. Study limitation. The samples were not representative.
CS
Cíle. Outcome Rating Scale (ORS) je velmi krátká sebehodnotící škála určená k měření změn během psychoterapie. Cílem této studie bylo ověřit (a) faktorovou strukturu ORS, (b) in-varianci měření mezi klinickým a neklinickým vzorkem, mezi hodnocením před léčbou a po léčbě (v rámci klinického vzorku) a mezi online a papírovou formou škály (v rámci neklinického vzorku), (c) souběžnou validitu s dalšími nástro-ji na měření výsledku psychoterapie a (d) citli-vost na terapeutickou změnu.Vzorek. Studie se zúčastnilo N = 256 pacientů, N = 210 neklinických respondentů a N = 89 stu-dentů. Pacienti vyplnili ORS před psychoterapií a po ní. Statistická analýza. Faktorová struktura a inva-riance měření byly ověřovány pomocí konfir-mační faktorové analýzy. Souběžná validita a stabilita v čase byly posuzovány pomocí kore-lační analýzy. Citlivost na změnu byla hodnoce-na pomocí indexu spolehlivé změny a velikosti účinku.Výsledky. Byla potvrzena jednodimenzionální struktura škály. Nejvhodnějším modelem byl částečně tau-ekvivalentní model s náboji první a čtvrté položky fixovanými na stejnou hod-notu. Zatímco mezi klinickým a neklinickým vzorkem byla potvrzena pouze metrická inva-riance, mezi hodnocením před a po léčbě škála vykazovala skalární invarianci a mezi online a papírovou formou přísnou invarianci. Vnitřní konzistence i souběžná validita byly uspokoji-vé. Citlivost na změnu psychoterapie byla ade-kvátní. Vnitřní konzistence a citlivost na změnu se zvýšila, pokud byl celkový skór počítán jako vážená suma položek.omezení studie. Vzorky nebyly reprezentativní.
12
Publication available in full text mode
Content available

General Self-Efficacy Associations with Personality and Motivation: Psychometric Properties and Measurement Invariance of the Polish New General Self-Efficacy Scale

63%
Baran L., Janowski M.
Studia Psychologica
|
2023
|
vol. 23
|
issue 1
15-29
PL
Celem niniejszego badania było określenie trafności i rzetelności polskiej wersji Nowej Skali Uogólnionego Poczucia Własnej Skuteczności (NGSE). W czterech różnych próbach (N = 1,837) dorośli respondenci wypełnili polską wersję NGSE (NGSEpl) w połączeniu z kwestionariuszami mierzącymi osobowość, motywację i tendencje behawioralne. Konfirmacyjna analiza czynnikowa wykazała dobre dopasowanie struktury jednoczynnikowej do danych. Współczynnik alfa Cronbacha wyniósł powyżej .87 we wszystkich próbach, a stabilność skali wyniosła .68. Niezmienność pomiarowa NGSEpl obliczona dla różnych grup wiekowych potwierdziła, że skala mierzy ten sam konstrukt w obu próbach. Wyniki NGSEpl były dodatnio powiązane z częstością korzystania z aktywnych strategii radzenia sobie, motywacją mistrzostwa, wszystkimi cechami modelu Wielkiej Piątki, a ujemnie z pasywnymi strategiami radzenia sobie. Wyniki uzyskanych analiz potwierdziły zatem rzetelność, stabilność i trafność NGSEpl.
EN
This study aimed to determine the validity and reliability of the Polish version of the New General Self-Efficacy Scale (NGSE). In four different samples (N = 1,837), adult respondents completed the Polish version of NGSE (NGSEpl) in combination with questionnaires assessing personality, motivation, and behavioral tendencies. Confirmatory factor analysis demonstrated a good fit for the one-factor structure. Cronbach's alpha was above .87 in all samples, and the stability of the scale was .68. Measurement invariance of NGSEpl calculated for different age groups confirmed that the scale measures the same construct in both samples. NGSEpl scores were positively related to the frequency of active coping strategies, mastery-goal orientation, and Big Five model traits and negatively to passive coping strategies. Results supported the reliability, stability, and validity of the NGSEpl.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.